Enhance a video prompt from optional multimodal context
Create an asynchronous text-only prompt-enhancement task. Successful tasks are charged after completion from actual input and output tokens; this call does not generate a video. The compatibility model field is ignored.
Request Body
application/jsonRequiredmetadataMetadataCaller-supplied metadata; ≤16 keys, key ≤64 chars, value ≤512 chars
callback_urlCallback UrlHTTPS URL Beatra will POST the final Task envelope to when the Task reaches a terminal state
callback_signing_key_idCallback Signing Key IdOptional standalone callback signing key. Omit for unsigned callback delivery; requires callback_url when provided.
modelModelCompatibility input only. Its value and type are ignored in the first release; Beatra resolves the available prompt-enhancement model internally.
"auto"promptRequired creative intent to expand into a production-ready video prompt.
1Maximum length: 7000durationTarget video duration in integer seconds.
4Maximum: 15aspect_ratioTarget video aspect ratio. Text-only requests cannot use adaptive.
"adaptive" | "21:9" | "16:9" | "4:3" | "1:1" | "3:4" | "9:16"first_frameFirst FrameOptional strict first-frame context image.
last_frameLast FrameOptional strict last-frame context image.
referencesReferencesOptional ordered image, video, or audio context. Reference mode and strict-frame mode are mutually exclusive.
Header Parameters
X-Request-IdstringOptional client request id echoed in the response.
Idempotency-Key1Maximum length: 128AuthorizationBearer API key.
Task accepted